We present an automatic method to track individual nodule progression in a lung cancer mouse model. Fourteen A/J mice received an intraperitoneal injection of urethane. Respiratory-gated micro-CT images of the lungs were taken 8, 22, and 37 weeks after injection, at which 195, 585 and 636 nodules were manually detected. The three images from every animal were registered and their nodules matched with average accuracy of 97.2%. All nodules detected at week 8 were then tracked until week 37, and volumetrically segmented to characterize the growth rate and doubling rate. Our framework is able to segment 92.9% of all nodules, ranging from the earliest stage (0.2mm) to advanced stage where nodule segmentation becomes challenging due to complex anatomy and nodule overlap. In conclusion, we showed the utility of the proposed framework to facilitate further research in pre-clinical lung cancer model.