Most of the proposed VLSI dictionary machines appearing in the literat
ure were designed to fit in one chip only. If the number of acquired e
lements is larger than that of VLSI cells, another chip has to be desi
gned and manufactured to take a larger dictionary into account. In thi
s paper, we propose a new design for dictionary machines that assemble
s blocks of standard existing dictionary machines. Our machine is as e
fficient as the best machines described in the literature, with the en
ormous advantage of scaling up quite easily, with no degradation of it
s performance, by simply adding more and more standard blocks.