This is a novel effort towards effective characterization of cervix lesions from CECT images. Two different approaches have been adopted for designing multi-objective binary GWO algorithms. For the utilized cases, Non-dominated Sorting based GWO dominates the other meta-heuristics based methods compared with. Cervix lesions are up to 91.1% accurately classified as benign and malignant with only five features selected by NSGWO. Efficiency of NSGWO is further verified on high-dimensional microarray gene expression datasets available online.