Previous studies have indicated that thyroid cancer risk after a first childhood malignancy is curvilinear with radiation dose, increasing at low to moderate doses and decreasing at high doses. Understanding factors that modify the radiation dose response over the entire therapeutic dose range is challenging and requires large numbers of subjects. We quantified the long-term risk of thyroid cancer associated with radiation treatment among 12,547 5-year survivors of a childhood cancer (leukemia, Hodgkin lymphoma and non-Hodgkin lymphoma, central nervous system cancer, soft tissue sarcoma, kidney cancer, bone cancer, neuroblastoma) diagnosed between 1970 and 1986 in the Childhood Cancer Survivor Study using the most current cohort follow-up to 2005. There were 119 subsequent pathologically confirmed thyroid cancer cases, and individual radiation doses to the thyroid gland were estimated for the entire cohort. This cohort study builds on the previous case-control study in this population (69 thyroid cancer cases with follow-up to 2000) by allowing the evaluation of both relative and absolute risks. Poisson regression analyses were used to calculate standardized incidence ratios (SIR), excess relative risks (ERR) and excess absolute risks (EAR) of thyroid cancer associated with radiation dose. Other factors such as sex, type of first cancer, attained age, age at exposure to radiation, time since exposure to radiation, and chemotherapy (yes/no) were assessed for their effect on the linear and exponential quadratic terms describing the dose-response relationship. Similar to the previous analysis, thyroid cancer risk increased linearly with radiation dose up to approximately 20 Gy, where the relative risk peaked at 14.6-fold (95% CI, 6.8-31.5). At thyroid radiation doses >20 Gy, a downturn in the dose-response relationship was observed. The ERR model that best fit the data was linear-exponential quadratic. We found that age at exposure modified the ERR linear dose term (higher radiation risk with younger age) (P < 0.001) and that sex (higher radiation risk among females) (P = 0.008) and time since exposure (higher radiation risk with longer time) (P < 0.001) modified the EAR linear dose term. None of these factors modified the exponential quadratic (high dose) term. Sex, age at exposure and time since exposure were found to be significant modifiers of the radiation-related risk of thyroid cancer and as such are important factors to account for in clinical follow-up and thyroid cancer risk estimation among childhood cancer survivors.