Query optimization is an invigorating task of any database system. A number of heuristics has been designed and implemented to optimize database queries. The imperishable developments in the field of Decision Support System (DSS) databases are presenting data at an exceptional rate. The massive volume of DSS data is consequential only when it is able to access and analyze. Here, an effort is made to optimize the system resources (Total Costs) required to execute a distributed DSS query. An innovative hybrid idea of Information Theory (Entropy) and restricted stochastic algorithm called Entropy based Restricted Stochastic Query Optimizer (ERSQO) has been used and implemented. The results of the proposed hybrid approach are compared with other DSS query optimizer techniques viz. Exhaustive Enumeration Query Optimizer (EAQO), Simple Genetic Query Optimizer (SGQO), Novel Genetic Query Optimizer (NGQO) and Restricted Stochastic Query Optimizer (RSQO). In addition, the effect of inter-site and intra-site parallelism on the design of query optimizer has also been examined. Finally, the results of different DSS query optimizer are statistically analyzed. The experimental study reveals that results obtained using ERSQO are 0.35%, 0.6% and 1.6% more consistent than RSQO, NGQO and SGQO respectively.