Background The triennial mortality rates for lung cancer in the two decades 1981–2001 in the province of Lecce, Italy, are significantly higher than those for the entire region of Apulia (to which the Province of Lecce belongs) and the national reference rates. Moreover, analyzing the rates in the three-year periods 1993–95, 1996–98 and 1999–01, there is a dramatic increase in mortality for both males and females, which still remains essentially unexplained: to understand the extent of this phenomenon, it is worth noting that the standardized mortality rate for males in 1999–01 is equal to 13.92 per 10000 person-years, compared to a value of 6.96 for Italy in the 2000–2002 period. These data have generated a considerable concern in the press and public opinion, which with little scientific reasoning have sometimes identified suspected culprits of the risk excess (for example, the emission caused by a number of large industrial sites located in the provinces of Brindisi and Taranto, bordering the Province of Lecce). The objective of this paper is to study on a scientifically sound basis the spatial distribution of risk for lung cancer mortality in the province of Lecce. Our goal is to demonstrate that most of the previous explanations are not supported by data: to this end, we will follow a hybrid approach that combines both frequentist and Bayesian disease mapping methods. Furthermore, we define a new sequential algorithm based on a modified version of the Besag-York-Mollie (BYM) model, suitably modified to detect geographical clusters of disease.