To identify differentially expressed genes (DEGs) in analysis of microarray data, a majority of existing filter methods rank gene individually. Such a paradigm could overlook the genes with trivial individual discriminant powers but significant powers of discrimination in their combinations. This paper proposed an impurity metric in which the number of split intervals for each feature is considered as a parameter to be optimized for gaining maximal discrimination. The proposed method was first evaluated by applying to a synthesized noisy rectangular grid dataset, in which the significant feature pair which forms a rectangular grid pattern was successfully recognized. Furthermore, applying to the identification of DEGs on colon microarray data, the proposed method demonstrated that it could become an alternative to Fisher's test for the prescreening of genes which led to better performance of the SVM-RFE method.