Embedded systems make a heavy use of software to perform Real-Time embedded control tasks. Embedded software is characterized by a relatively long lifetime and by tight cost, performance and safety constraints. Several super-optimization techniques for embedded software based on Multi-valued Decision Diagram (MDD) representations have been described in the literature, but they all share the same basic limitation. They are based on standard Ordered MDD (OMDD) packages, and hence require a fixed order of evaluation for the MDD variables on every execution path. Free MDDs (FMDDs) lift this limitation, and hence open up more optimization opportunities. Finding the optimal variable ordering for FMDDs is a very difficult problem. Hence in this paper we describe a heuristic procedure that performs well in practice, and is based on FMDD cost estimation applied to recursive co-factoring. Experimental results show that our new variable ordering method obtains often smaller embedded software than previous (sifting-based) methods.