Purpose Studies have reported an association between hospital volume and survival for non–small-cell lung cancer (NSCLC). We explored this association in England, accounting for case mix and propensity to resect. Methods We analyzed data on 134,293 patients with NSCLC diagnosed in England between 2004 and 2008, of whom 12,862 (9.6%) underwent surgical resection. Hospital volume was defined according to number of patients with resected lung cancer in each hospital in each year of diagnosis. We calculated hazard ratios (HRs) for death in three predefined periods according to hospital volume, sex, age, socioeconomic deprivation, comorbidity, and propensity to resect. Results There was increased survival in hospitals performing > 150 surgical resections compared with those carrying out < 70 (HR, 0.78; 95% CI, 0.67 to 0.90; P_trend < .01). The association between hospital volume and survival was present in all three periods of follow-up, but the magnitude of association was greatest in the early postoperative period. Conclusion High-volume hospitals have higher resection rates and perform surgery among patients who are older, have lower socioeconomic status, and have more comorbidities; despite this, they achieve better survival, most notably in the early postoperative period.